Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    views
    -0.06
    621
    -0.06
     performances
    -0.06
     radiator
    -0.06
     impeccable
    -0.06
    .Password
    -0.06
    .activ
    -0.06
     wheelchair
    -0.06
    Presence
    -0.06
    /access
    -0.06
    POSITIVE LOGITS
     salope
    0.07
     Ashe
    0.07
    ethoven
    0.06
    ุทธ
    0.06
    ２０
    0.06
    STER
    0.06
     Catalan
    0.06
     Isles
    0.06
    ,...
    0.06
    noun
    0.06
    Act Density 0.010%

    No Known Activations